© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14548
    Prev
    Next
    INDEX
    Explanations

    .com, .edu, e-mail, contact, address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zin
    -0.21
    é¢Ŀ
    -0.21
    没æľīå¿ħè¦ģ
    -0.18
    模
    -0.18
    çĥľ
    -0.18
    ãģªãĤĤãģ®
    -0.17
     distilled
    -0.17
    æĹłäºº
    -0.17
    case
    -0.17
    KIT
    -0.17
    POSITIVE LOGITS
    åĴĮä»ĸçļĦ
    0.24
    æĺ¯ä»ĸ
    0.21
    ä»ĸ对
    0.20
    çĥŃå¿ĥ
    0.19
     errs
    0.19
    ãģ»ãģĭ
    0.19
    好åıĭ
    0.19
    urrence
    0.19
    -worker
    0.18
    awi
    0.18
    Activations Density 0.023%

    No Known Activations